AI TOOLS RADAR
All models / FIREWORKS
fireworks logo
fireworks

Fireworks: Ember-1

Source description (English)

Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

View source on OpenRouter
Overview

Model specifications

Context
1,048,576 tokens
Maximum output
943,718 tokens
Architecture
text+image->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$3
per 1M tokens
Output
$15
per 1M tokens
Cache read
$0.3
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
max
Capabilities
max, high, low
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"fireworks/ember-1","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
Reasoning

Yes · max · high · low

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokenspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

1 Provider

Checked: September 24, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Fireworks

Not provided
Context
1.0M
Maximum output
944K
Input
$3
Output
$15
Cache read
$0.3
Cache write
Not provided